A Multi-strategy Word Sense Disambiguation Method

摘要：

　　Word sense disambiguation (WSD) is a critical and difficult issue in natural language processing(NLP),as well as WSD is great significance in large area of research areas of NLP.This paper presents a method of multi-word sense disambiguation strategy.The method combines the method based on match word corpus and the method based on the similarity and relevance very well.While the calculation of similarity and relevance are make full use of the sememe-tree information from HowNet.The experiments show that the proposed WSD method can obtain better results.

关键词： Word Sense Disambiguation HowNet Collocation Store Similarity Relevance

作者: Linlin Yu Dengfeng Xu Lifang Song Guojie Li Xudong Song

作者单位: Dalian Institute of Science and Technology,Dalian,China Dalian HTHX Technology Limited Company,Dalian,China Dalian HengYi Technology Limited Company,Dalian,China Dalian Jiaotong University,Dalian,China

会议类型: 国际会议

会议名称: 2012 International Applied Mechanics,Mechatronics Automation Symposium(2012应用力学,机电一体化自动化国际研讨会)(IAMMAS2012)

会议地点: 沈阳

会议语种:英文

页码: 2109-2112

在线出版日期: 2012-09-07（万方平台首次上网日期，不代表论文的发表时间）